• Title/Summary/Keyword: text-to-image

Search Result 892, Processing Time 0.027 seconds

A Direction Computation and Media Retrieval Method of Moving Object using Weighted Vector Sum (가중치 벡터합을 이용한 이동객체의 방향계산 및 미디어 검색방법)

  • Suh, Chang-Duk;Han, Gi-Tae
    • The KIPS Transactions:PartD
    • /
    • v.15D no.3
    • /
    • pp.399-410
    • /
    • 2008
  • This paper suggests a new retrieval method using weighted vector sum to resolve a problem of traditional location-based retrieval method, nearest neighbor (NN) query, and NN query using direction. The proposed method filters out data with the radius, and then the remained retrieval area is filtered by a direction information compounded of a user's moving direction, a pre-fixed interesting direction, and a pre-fixed retrieval angle. The moving direction is computed from a vector or a weighted vector sum of several vectors using a weight to adopt several cases. The retrieval angle can be set from traditional $360^{\circ}$ to any degree you want. The retrieval data for this method can be a still and moving image recorded shooting location, and also several type of media like text, web, picture offering to customer with location of company or resort. The suggested method guarantees more accurate retrieval than traditional location-based retrieval methods because that the method selects data within the radius and then removes data of useless areas like passed areas or an area of different direction. Moreover, this method is more flexible and includes the direction based NN.

Exploring Epistemological Features Presented in Texts of Exhibit Panels in the Science Museum (과학관의 전시 패널 글에 반영된 과학의 인식론적 측면 탐색)

  • Lee, Sun-Kyung;Shin, Myeong-Kyeong;Lee, Gyu-Ho;Choi, Chui-Im;Baek, Doo-Sung;Chung, Kwang-Hoon;Yu, Man-Sun;Kim, Sun-Ja;Son, Sung-Keun;Choi, Hyun-Sook;Lee, Kang-Hwan;Lee, Jeong-Gu
    • Journal of the Korean earth science society
    • /
    • v.32 no.1
    • /
    • pp.124-139
    • /
    • 2011
  • This study was to explore epistemological features presented in texts of exhibit panels in the science museum located in Gyeonggi Province. Out-of-school or daily experiences allow more properly and potentially students to form informative science image, because the understandings of scientific epistemology were constructed tacitly through various experiences over a long period of time. The target for this study was panel texts of exhibits in a science museum as an of out-of-school context. The analytical framework was adopted from epistemological frameworks by Ryder et al. (1999). The research results were explored in the categories of relationship between scientific knowledge claims and the data, the nature of lines of scientific enquiry, and social dimension of science. It revealed that one exhibit might reflect the characteristics of one epistemological position: relating one data to one knowledge claim; generating knowledge claim from scientists' individual interests or from discipline's internal epistemology; scientists working as a community or an institution. Findings suggested that the exhibits of a science museum including panel texts and medium need to reflect the wide ranges of scientific epistemology.

The Relationship of Nearly White Background Colors and Readability of Tablet PC (Tablet PC에서 Nearly White 배경색과 가독성의 관계)

  • Yun, Bo-Ram;Park, YungKyung
    • Science of Emotion and Sensibility
    • /
    • v.17 no.2
    • /
    • pp.35-44
    • /
    • 2014
  • The purpose of this paper is to investigate the readability of Nearly White background color in display environment. To perform the experiment, warmup experiment was carried out to for cognitive of whiteness using a Tablet PC. The experiment environment was by a indoor window seat under a mixture of fluorescent light and sunlight. The result of previous test was that the most whiteness perception was a color white a medium wavelength and followed by the short wavelength. The main experiment was to find readability, color combination and visual strains using 4 nearly whites background colors (Reddish, Greenish, Blueish, Yellowish) and one white background color, also text color is limited on black. As a result, readability and color combination had the highest score against a Greenish white background. Visual strain is also the lowest against a Greenish background. On the contrary, readability and color combination preference has the lowest score against the Reddish background. Visual strain is also the highest against a Reddish background. We propose the background color, which improves readability and reduces visual strain in visual display terminals environment through the research results.

Design and Implementation of user centric pavilion information guide system based on commercial mobile device (모바일 기기 기반 사용자 중심형 전시관 정보 안내 시스템의 설계 및 구현)

  • Yun Hyun-Joo;Bu So-Young;Choi Yoo-Joo
    • Journal of the Korea Society of Computer and Information
    • /
    • v.11 no.2 s.40
    • /
    • pp.187-199
    • /
    • 2006
  • This paper proposes the design of user centric pavilion information guide system based on mobile device such as PDA. which is composed of system interface factors as user wants. The suggested information guide system is convenient for user carrying because it is based on PDA mobile device and the used liquid browser system makes all data information displayed on a small screen in contrast with the other browser system. Indeed, factors of system interface can be re-composed by user interaction. And this system can effectively provide the detail information about the exhibited objects as various media data such as text, image, voice, music, video etc. The proposed system is made up of media database server. mobile system control server and mobile system interface which accepts user interaction and displays the information. Each system is networked based on TCP/IP and uses XML (extensible Markup Language) and JAVA 2 micro edition to be able to update data. This feature enhances a wide use to be able to load this system on the any mobile device.

  • PDF

Implementation of Character and Object Metadata Generation System for Media Archive Construction (미디어 아카이브 구축을 위한 등장인물, 사물 메타데이터 생성 시스템 구현)

  • Cho, Sungman;Lee, Seungju;Lee, Jaehyeon;Park, Gooman
    • Journal of Broadcast Engineering
    • /
    • v.24 no.6
    • /
    • pp.1076-1084
    • /
    • 2019
  • In this paper, we introduced a system that extracts metadata by recognizing characters and objects in media using deep learning technology. In the field of broadcasting, multimedia contents such as video, audio, image, and text have been converted to digital contents for a long time, but the unconverted resources still remain vast. Building media archives requires a lot of manual work, which is time consuming and costly. Therefore, by implementing a deep learning-based metadata generation system, it is possible to save time and cost in constructing media archives. The whole system consists of four elements: training data generation module, object recognition module, character recognition module, and API server. The deep learning network module and the face recognition module are implemented to recognize characters and objects from the media and describe them as metadata. The training data generation module was designed separately to facilitate the construction of data for training neural network, and the functions of face recognition and object recognition were configured as an API server. We trained the two neural-networks using 1500 persons and 80 kinds of object data and confirmed that the accuracy is 98% in the character test data and 42% in the object data.

Trend of Research and Industry-Related Analysis in Data Quality Using Time Series Network Analysis (시계열 네트워크분석을 통한 데이터품질 연구경향 및 산업연관 분석)

  • Jang, Kyoung-Ae;Lee, Kwang-Suk;Kim, Woo-Je
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.5 no.6
    • /
    • pp.295-306
    • /
    • 2016
  • The purpose of this paper is both to analyze research trends and to predict industrial flows using the meta-data from the previous studies on data quality. There have been many attempts to analyze the research trends in various fields till lately. However, analysis of previous studies on data quality has produced poor results because of its vast scope and data. Therefore, in this paper, we used a text mining, social network analysis for time series network analysis to analyze the vast scope and data of data quality collected from a Web of Science index database of papers published in the international data quality-field journals for 10 years. The analysis results are as follows: Decreases in Mathematical & Computational Biology, Chemistry, Health Care Sciences & Services, Biochemistry & Molecular Biology, Biochemistry & Molecular Biology, and Medical Information Science. Increases, on the contrary, in Environmental Sciences, Water Resources, Geology, and Instruments & Instrumentation. In addition, the social network analysis results show that the subjects which have the high centrality are analysis, algorithm, and network, and also, image, model, sensor, and optimization are increasing subjects in the data quality field. Furthermore, the industrial connection analysis result on data quality shows that there is high correlation between technique, industry, health, infrastructure, and customer service. And it predicted that the Environmental Sciences, Biotechnology, and Health Industry will be continuously developed. This paper will be useful for people, not only who are in the data quality industry field, but also the researchers who analyze research patterns and find out the industry connection on data quality.

Implementation of CoMirror System with Video Call and Messaging Function between Smart Mirrors (스마트 미러간 화상 통화와 메시징 기능을 가진 CoMirror 시스템 구현)

  • Hwang, Kitae;Kim, Kyung-Mi;Kim, Yu-Jin;Park, Chae-Won;Yoo, Song-Yeon;Jung, Inhwan;Lee, Jae-Moon
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.22 no.6
    • /
    • pp.121-127
    • /
    • 2022
  • Smart mirror is an IoT device that attaches a display and an embedded computer to the mirror and provides various information to the useer along with the mirror function. This paper went beyond the form of dealing with smart mirrors only stand alone device the provide information to users, and constructed a network in which smart mirrors are connected, and proposed and implemented a CoMirror system that allows users to talk and share information with other smart mirror users. The CoMirror system has a structure in which several CoMirror clients are connected on one CoMirror server. The CoMirror client consists of Raspberry Pi, a mirror film, a touch pad, a display device, an web camera, etc. The server has functions such as face learning and recognition, user management, a relay role for exchanging messages between clients, and setting up for video call. Users can communicate with other CoMirror users via the server, such as text, image, and audio messages, as well as 1:1 video call.

Analysis of Generative AI Technology Trends Based on Patent Data (특허 데이터 기반 생성형 AI 기술 동향 분석)

  • Seongmu Ryu;Taewon Song;Minjeong Lee;Yoonju Choi;Soonuk Seol
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.17 no.1
    • /
    • pp.1-9
    • /
    • 2024
  • This paper analyzes the trends in generative AI technology based on patent application documents. To achieve this, we selected 5,433 generative AI-related patents filed in South Korea, the United States, and Europe from 2003 to 2023, and analyzed the data by country, technology category, year, and applicant, presenting it visually to find insights and understand the flow of technology. The analysis shows that patents in the image category account for 36.9%, the largest share, with a continuous increase in filings, while filings in the text/document and music/speech categories have either decreased or remained stable since 2019. Although the company with the highest number of filings is a South Korean company, four out of the top five filers are U.S. companies, and all companies have filed the majority of their patents in the U.S., indicating that generative AI is growing and competing centered around the U.S. market. The findings of this paper are expected to be useful for future research and development in generative AI, as well as for formulating strategies for acquiring intellectual property.

Increasing Accuracy of Stock Price Pattern Prediction through Data Augmentation for Deep Learning (데이터 증강을 통한 딥러닝 기반 주가 패턴 예측 정확도 향상 방안)

  • Kim, Youngjun;Kim, Yeojeong;Lee, Insun;Lee, Hong Joo
    • The Journal of Bigdata
    • /
    • v.4 no.2
    • /
    • pp.1-12
    • /
    • 2019
  • As Artificial Intelligence (AI) technology develops, it is applied to various fields such as image, voice, and text. AI has shown fine results in certain areas. Researchers have tried to predict the stock market by utilizing artificial intelligence as well. Predicting the stock market is known as one of the difficult problems since the stock market is affected by various factors such as economy and politics. In the field of AI, there are attempts to predict the ups and downs of stock price by studying stock price patterns using various machine learning techniques. This study suggest a way of predicting stock price patterns based on the Convolutional Neural Network(CNN) among machine learning techniques. CNN uses neural networks to classify images by extracting features from images through convolutional layers. Therefore, this study tries to classify candlestick images made by stock data in order to predict patterns. This study has two objectives. The first one referred as Case 1 is to predict the patterns with the images made by the same-day stock price data. The second one referred as Case 2 is to predict the next day stock price patterns with the images produced by the daily stock price data. In Case 1, data augmentation methods - random modification and Gaussian noise - are applied to generate more training data, and the generated images are put into the model to fit. Given that deep learning requires a large amount of data, this study suggests a method of data augmentation for candlestick images. Also, this study compares the accuracies of the images with Gaussian noise and different classification problems. All data in this study is collected through OpenAPI provided by DaiShin Securities. Case 1 has five different labels depending on patterns. The patterns are up with up closing, up with down closing, down with up closing, down with down closing, and staying. The images in Case 1 are created by removing the last candle(-1candle), the last two candles(-2candles), and the last three candles(-3candles) from 60 minutes, 30 minutes, 10 minutes, and 5 minutes candle charts. 60 minutes candle chart means one candle in the image has 60 minutes of information containing an open price, high price, low price, close price. Case 2 has two labels that are up and down. This study for Case 2 has generated for 60 minutes, 30 minutes, 10 minutes, and 5minutes candle charts without removing any candle. Considering the stock data, moving the candles in the images is suggested, instead of existing data augmentation techniques. How much the candles are moved is defined as the modified value. The average difference of closing prices between candles was 0.0029. Therefore, in this study, 0.003, 0.002, 0.001, 0.00025 are used for the modified value. The number of images was doubled after data augmentation. When it comes to Gaussian Noise, the mean value was 0, and the value of variance was 0.01. For both Case 1 and Case 2, the model is based on VGG-Net16 that has 16 layers. As a result, 10 minutes -1candle showed the best accuracy among 60 minutes, 30 minutes, 10 minutes, 5minutes candle charts. Thus, 10 minutes images were utilized for the rest of the experiment in Case 1. The three candles removed from the images were selected for data augmentation and application of Gaussian noise. 10 minutes -3candle resulted in 79.72% accuracy. The accuracy of the images with 0.00025 modified value and 100% changed candles was 79.92%. Applying Gaussian noise helped the accuracy to be 80.98%. According to the outcomes of Case 2, 60minutes candle charts could predict patterns of tomorrow by 82.60%. To sum up, this study is expected to contribute to further studies on the prediction of stock price patterns using images. This research provides a possible method for data augmentation of stock data.

  • PDF

A study of the destructive styles from Contemporary Paintings - Focused on distinguishing enmity-destruction and self-destruction - (현대회화에서 드러난 해체의 형식론에 관한 연구 -타의적 해체와 자의적 해체의 성격규정을 중심으로-)

  • Park Ki-Woong
    • Journal of Science of Art and Design
    • /
    • v.7
    • /
    • pp.5-63
    • /
    • 2005
  • Generally, the meanings of destruction are related in the meaning of demolition, breakdown, into fragments ... and so on, and the similar meanings are twist, crush, demolish, split, cut, into pieces , break up ... etc. Further, it has related in the cruelty and destructive heart which are linked with orgy, Sadism, Necrophilia and so on. The meanings are also expressed by the initial , which are deprivation, deface, defame, deform, degrade, delegitimize, denounce , deride, destroy, devalue, as well as debase, debunk, declaim, declassify, decry, delete, denigrate, deprecate, despise or detract ...and so on. Dario Gamboni has discussed the meaning in his book as two categories Iconoclasm and Vandalism. And the similar meanings could be found in the words which has the initial of , like abase, abate, abhor, abjure, abolish, abridge, abuse ...and so on. Even though the distinct meanings of Iconoclasm and Vandalism, it is not easy to distinguish clearly between the differences when the results are accomplished in contemporary paintings because of the similarity of the results. In korean vocabulary there are no similar words to distinguish between the meanings of destruction and deconstruction, and the deconstruction is not recorded in the general dictionaries. However the meaning of is diminishing, separation, contrast and so on. So the unification of the word as do-construction is not construct, minus construction, reverse construction. And Vincent Ditch explained that there are the meaning of destroy the text. From Jacques Derrida, the deconstruction strategy is to criticise the world of traditional metaphysics and logocentrism, and not to reconstruire the philosophical meaning of texts but $d\'{e}construire$ them. And Saussure emphasized that the signifers could have more meaning that there can be more signified in traditional texts in the art. as a result, deconstruction is explained that there are many signified meanings in a signifer. In this thesis , from using the meanings of destruction and deconstruction, to distinguish the expressive skills in contemporary art works are arising. Therefore, special methods which are linked in the destruction styles are selected. As a result, the two different purposes of destruction is arising, one is enmity destruction and the other is self destruction another word, auto destruction or destruction to create The enmity destruction can be distinguished by the two category Iconoclasm and Vandalism. They come from the moment of different historical aspect is arising and want to attack the Icon or masterpiece this concept is from the study of John Philips and especially iconoclasm is linked with religious and artistic heart, but Vandalism is come from the political attack. Sometime, this distinguish is not clearly arising, because the two aspects are co-related in the attack. As a result, firstly, the Iconoclastic controversy had arisen in the methods of Dadaism which has developed by Man Ray, Francis Picabia and Marcel Duchamp. They want to attack the pre-established master-pieces and painting spaces, and they had 'non-artistic attitude' not to be art. Since 1980, the German artist Anselm Kiefer adapted the methods and made them his special skills so he had tried to paint tough brush strokes and draw with hugh pallette image line and fire and water images , they can be the image attack as the Iconoclasm. secondly, the model of vandalism is to be done by hammer, drill, canon and so on. the method is to attack the content of painting. Further, the object of destruction is bound by cords and iron lings to demolish or to declare the authority of pre-statues; it symbolize the pre-authority is gone already. Self-destruction based paintings are clearly different in the purpose of approaching the art work. First of all, they can be auto-destruction, creative destruction and metamorphosis destruction, which is linked with the skill the material aspect and basic stature, and sign destruction or signifier destruction, which is link with the inner meaning destruction that is considered as the Semiotical destruction in post-modern paintings. Since 1960, the auto destruction is based on the method of firing, melting, grinding and similar skills, which is linked with Neo-Dada and reverse-assemblage. Metamorphosis destruction is strongly linked with the basic inner heart price and quality, so it can be resulted in the changedness of expectation and recognition. Tony Cragg has developed the skills to metamorphose the wood as stone or iron as cloth and stone as sponge and rubber and so on. The researcher has developed the same style in the series of since 2003. The other self-destructive methods are found in the skill of sign destruction. In the methods the meaning of the art is not fixed as one or two, but is developed multi-meaning and differ from original starting situation, so Jacques Derrida called the difference meaning in deconstruction. It is the destruction of textes. These methods are accomplished by David Salle, Francesco Clemente, and recently Tracy Emin, who has developed the attacking heart in the spectators' emotion. Sometime in the method of self-destruction, it is based on horror and shock, the method is explored by Demian Hirst and Jakes and Dinos Chapman. Their destructive styles stimulate ambivalent heart and destroy original sign of girl and animals.

  • PDF